WO2005041125A1 - Programme, dispositif et procede de correction de distorsion d'image et support d'enregistrement comportant un programme de correction de distorsion d'image - Google Patents

Programme, dispositif et procede de correction de distorsion d'image et support d'enregistrement comportant un programme de correction de distorsion d'image Download PDF

Info

Publication number
WO2005041125A1
WO2005041125A1 PCT/JP2004/002825 JP2004002825W WO2005041125A1 WO 2005041125 A1 WO2005041125 A1 WO 2005041125A1 JP 2004002825 W JP2004002825 W JP 2004002825W WO 2005041125 A1 WO2005041125 A1 WO 2005041125A1
Authority
WO
WIPO (PCT)
Prior art keywords
projection
geodesic
line
paper
image
Prior art date
Application number
PCT/JP2004/002825
Other languages
English (en)
Japanese (ja)
Inventor
Katsuhito Fujimoto
Misako Suwa
Hiroaki Takebe
Satoshi Naoi
Original Assignee
Fujitsu Limited
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujitsu Limited filed Critical Fujitsu Limited
Priority to JP2005514903A priority Critical patent/JP4047352B2/ja
Publication of WO2005041125A1 publication Critical patent/WO2005041125A1/fr
Priority to US11/359,096 priority patent/US7471848B2/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/80—Geometric correction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/06—Topological mapping of higher dimensional structures onto lower dimensional surfaces
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/60—Rotation of whole images or parts thereof
    • G06T3/608—Rotation of whole images or parts thereof by skew deformation, e.g. two-pass or three-pass rotation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
    • H04N1/387—Composing, repositioning or otherwise geometrically modifying originals

Definitions

  • Image distortion correction program image distortion correction device, image distortion correction method, and recording medium storing image distortion correction program
  • the present invention relates to a technique for correcting three-dimensional distortion of an image with high accuracy.
  • non-contact image capturing devices such as CCDs (Charge Coupled Devices) and digital cameras are used to input forms and paper documents at high speed and comfortably with the aim of streamlining input operations.
  • CCDs Charge Coupled Devices
  • the technology has been put to practical use.
  • the use of a non-contact type image pickup device makes it possible to write on the paper even during image input, compared to a contact type image pickup device such as an image scanner. It is possible to enjoy such comforts as possible.
  • the present invention can cope with various types of distortion by estimating a curved surface of a sheet using the contents (contents) of the sheet as a clue. It is another object of the present invention to provide an image distortion correction technology that enables distortion correction even when only a part of the paper surface appears in an image. Disclosure of the invention
  • a projection set of geodesic lines that are parallel to each other on the curved surface of the paper is extracted from the image of the paper surface, using the contents of the paper as a clue, and the geodesic line of the geodesic line is extracted From the projection set, the projection set of the ruled line forming the ruled surface corresponding to the paper surface is extracted. Then, the paper surface is estimated from the set of projections of the extracted geodesic line and ruled line, and the image distortion is corrected based on the paper surface.
  • the curved surface of the paper is estimated by using the content of the paper as a clue as compared with the distortion correction using the contour of the paper as a clue, it is possible to cope with various types of distortion, and the image can be printed on the paper.
  • High-precision distortion correction can be performed even from an input image in which only a part of the input image appears.
  • the projection set of the ruled line is calculated using the geometric property that the ratio of the length of the line segment obtained by cutting the ruled line projection by the geodesic projection from the extracted projection set of the geodesic line is constant. It is desirable to extract by searching. At this time, geodesic projections that do not satisfy the geometric property that the slope of the tangent line of the ruled line projection at the intersection of the ruled line projection and the geodesic projection is excluded from the extracted geodesic projection set Then, it is desirable to extract the projection set of the ruled line. In this way, it is possible to determine the authenticity of the extracted geodesic projection, and it is possible to extract a parallel geodesic line that is robust against noise.
  • the paper surface is estimated by estimating the width between the top and bottom geodesic projections from the set of extracted geodesic and ruled-line projections. It is desirable to estimate by solving a quadratic equation for the number of ruled lines derived using. At this time, it is desirable to estimate the width between the top geodesic projection and the bottom geodesic projection from the majority rule of the angle between the ruled line on the curved surface of the paper and the image capturing direction.
  • the projection set of the line of sight is calculated using the extracted projection set of the geodesic line. It is desirable to search and extract from the set of line-of-sight lines where the internal division ratio by the internal geodesic projection located between them and the bottom is constant, the one that minimizes the total deviation from the internal division ratio. Good.
  • the paper surface is estimated by using the imaging height with respect to the paper surface, and the geometrical property that the tangent of the geodesic line at the upper end and the lower end that intersects one line is parallel. In this way, more accurate distortion correction can be performed in consideration of perspective distortion caused by a non-contact imaging device such as a digital camera.
  • FIG. 1 is a configuration diagram of an image distortion correction device embodying the present invention.
  • FIG. 2 is an explanatory diagram of the center folding / sinking distortion to be corrected.
  • FIG. 3 is an explanatory diagram of the center folding floating distortion to be corrected.
  • FIG. 4 is an explanatory diagram of a vertex floating distortion to be corrected.
  • FIG. 5 is an explanatory diagram of distortion of a book to be corrected.
  • FIG. 6 is a flowchart showing processing contents in the image distortion correction device.
  • FIG. 7 is an explanatory diagram of an input image including image distortion.
  • FIG. 8 is an explanatory diagram of an image in which a projection set of geodesic lines is extracted.
  • FIG. 9 is an explanatory diagram of an image in which a projection set of a ruled line is extracted.
  • FIG. 10 is an explanatory diagram of a corrected image in which image distortion has been corrected.
  • FIG. 11 is an explanatory diagram showing a model of a curved surface of paper.
  • FIG. 12 is an explanatory diagram of a method for extracting a geodesic projection.
  • FIG. 13 is an explanatory diagram of a method of extracting a ruled line projection.
  • FIG. 14 is an explanatory diagram of the properties of ruled lines used for searching for geodesic projection correspondence.
  • FIG. 15 is an explanatory diagram of a projection of a curved surface of the paper surface and a developed paper surface obtained by flattening the projection.
  • FIG. 16 is an explanatory diagram showing another model of the curved surface of paper. BEST MODE FOR CARRYING OUT THE INVENTION
  • an image distortion correction device embodying the present invention includes an original image input unit 10 and a geodesic projection extraction unit 12 as shown in FIG. , A ruled line projection extraction unit 14, a paper curved surface estimation unit 16, an image distortion correction unit 18, and a corrected image output unit 20.
  • the image distortion correction device is built on a computer system having at least a central processing unit and a memory, and various functions for correcting the image distortion are realized by an image distortion correction program loaded in the memory. .
  • the original image input unit 10 is provided with a function of inputting an image of a sheet of paper via a non-contact image capturing device such as a digital camera or a contact type image capturing device such as an image scanner.
  • the image input is not limited to a configuration in which an image is input in real time from an image capturing apparatus, but a configuration in which a designated image is input from among captured images recorded on various recording media. Is also good.
  • the functions provided from the original image input unit 10 realize an image input function and an image input unit, respectively.
  • the geodesic projection extraction unit 12 provides a function to extract a set of geodesic projections that are parallel to each other on the curved surface of the paper from the image input by the original image input unit 10 (hereinafter referred to as “input image”). Is done.
  • the extraction of a geodesic projection set is realized by, for example, extracting a plurality of character strings or drawing lines that can be regarded as geodesic lines from an input image, and calculating a set of lines projected on a two-dimensional plane.
  • the functions provided by the geodesic projection extraction unit 12 implement the geodesic projection extraction function, the geodesic projection extraction means, and the geodesic projection extraction step, respectively.
  • the geodesic line extracted by the geodesic projection extraction unit 12 From the projection set, the geometric property of the geodesic line, "the ratio (ratio vector) of the line segment length obtained by cutting the ruled line projection by geodesic projection, is constant" or "the interior located between the upper and lower ends
  • the function of searching and extracting the projection set of ruled lines is provided using “the internal division ratio of the line of sight line projection by geodesic projection is constant”.
  • a three-dimensional curved surface formed by bending the paper surface is generally called a “wire surface”, and for any point on that surface, there is a straight line (wire line) on the curved surface passing through that point. It is known to do so.
  • the function provided by the ruled line projection extraction unit 14 implements a ruled line projection extraction function, a ruled line projection extraction unit, and a ruled line projection extraction step.
  • the paper surface estimating unit 16 estimates the paper surface in the input image from the projection set of the geodesic line and the ruled line extracted by the geodesic projection extracting unit 12 and the ruled line projection extracting unit 14, respectively.
  • the width between the upper end and the lower end of the parallel geodesic curve when the paper surface is extended flat is estimated based on the majority rule of the angle between the ruled line on the paper surface and the image capturing direction.
  • the paper surface is estimated by solving the quadratic equation for the number of ruled lines derived using the numerical differentiation and integration method from the geometric properties of the parallel geodesic curves.
  • the equation derived from the imaging height with respect to the paper surface and the geometric properties of the parallel geodesic line "the tangent of the geodesic line at the top and bottom that intersects one line of insight is parallel"
  • the paper surface estimation unit 16 realize the paper surface estimation function, the paper surface estimation means, and the paper surface estimation step, respectively.
  • the image distortion correction unit 18 provides a function of correcting image distortion by associating pixels with the input image based on the paper surface estimated by the paper surface estimation unit 16. .
  • the function provided by the image distortion correction unit 18 implements a distortion correction function, a distortion correction unit, and a distortion correction step.
  • the corrected image output unit 20 provides a function of outputting the input image corrected by the image distortion correction unit 18 (hereinafter, referred to as “corrected image”).
  • the image output is not limited to a configuration for outputting to a function of executing various image processing using the corrected image, and may be a configuration for storing the corrected image in various recording media.
  • the image distortions to be corrected by the image distortion correction device include “center folding sinking” and “center folding,” which occur on the paper with a fold in the center as shown in FIGS. 2 and 3.
  • the ups and downs of the vertices shown in Fig. 4 show that the upper left of the paper is raised.
  • the distortion of a book is a distortion caused by an image of a thick book such as a dictionary, a technical book, a handbook, etc. taken from an obliquely upper side by a non-contact image capturing device. (Distortion) and the distortion caused by the book itself being a three-dimensional curved surface.
  • step 1 (abbreviated as “S 1” in the figure, the same applies hereinafter), an input image to be corrected is input via a function provided by the original image input unit 10. That is, as shown in FIG. 7, an input image whose paper surface is smoothly distorted is read from the image pickup device or various recording media.
  • step 2 from the input image input by the original image input unit 10 via the function provided by the geodesic projection extraction unit 12, they were parallel to each other on the curved surface of the paper as shown in FIG. A geodesic projection set is extracted.
  • step 3 through the function provided by the ruled-line projection extraction unit 14, from the geodesic projection set extracted by the geodesic-projection extraction unit 12, as shown in FIG. A projection set is extracted.
  • step 4 the geodesic projection extraction unit 12 and the weaving line projection extraction unit 14 extract the geodesic and ruled line projection sets extracted from the projection set The paper surface in the input image is estimated.
  • step 5 the distortion of the input image is corrected as shown in FIG. 10 based on the paper surface estimated by the paper surface estimation unit 16 via the function provided by the image distortion correction unit 18. Is done.
  • Step 6 the corrected image corrected by the image distortion correcting unit 18 is output via the function provided by the corrected image output unit 20.
  • a projection set of geodesic lines parallel to each other on a curved surface of paper is extracted from the input image, and a ruled line is extracted from the projection set of geodesic lines.
  • a ruled line is extracted from the projection set of geodesic lines.
  • the paper surface is estimated from the projection set of the geodesic line and the ruled line, and the image distortion is corrected based on the paper surface.
  • the curved surface of the paper is estimated using the paper content as a clue compared to the distortion correction using the paper contour as a clue. High-precision distortion correction can be performed even from input images that only appear.
  • a paper surface is a ruled surface that satisfies the property that for any point on the surface, there is a straight line (wire line) on the surface passing through that point.
  • a straight line wire line
  • a parallel line on a flat paper surface becomes a parallel geodesic line on a curved surface of the paper.
  • p (s) and q (s) are the top and bottom geodesic lines on the curved surface of the paper, respectively.
  • a projection set of a geodesic line is extracted based on a character string or a ⁇ line extracted from an input image. Specifically, after extracting the components (character components) constituting the characters in the input image or the line segments composing the S-line, by combining the character components or the line segments that are close to each other, the projection set of the geodesic line is obtained. Can be extracted.
  • a curved surface formed by bending the paper surface is generally called a “line weave surface”, and for any point on that surface, there is a straight line (wire line) on the curved surface passing through that point.
  • the ratio of the line segment lengths (ratio vectors) obtained by dividing the ruled line projection by the geodesic projection” is constant. Is extracted. That is, as shown in FIG.
  • Property 1 The ratio of the line segment length obtained by cutting the ruled line projection by geodesic projection (compared to the vector) is 1
  • the paper surface shown in the input image is stretched flat, the paper surface is estimated from the geometric properties of the geodesic line by estimating the width (unknown constant) of the top and bottom geodesic projections. .
  • the quadratic equation for the number of ruled lines derived using the numerical differentiation and integration method can be solved, and the paper surface can be obtained.
  • the image capturing device was directly faced with a paper document, and the image was captured by orthographic projection.
  • the correspondence between the projection (ie, the image) of the curved surface of the paper surface and the developed paper surface when it is stretched flat is as shown in FIG.
  • the projection set of parallel geodesics on the paper surface projection has the property of becoming parallel lines even on the development paper. Therefore, let h be the width of the parallel geodesic lines at the top and bottom of the development paper.
  • l (xp) be the length of the ruled line projection from the top geodesic projection to the bottom geodesic projection.
  • the length from the left end weaving line to the point corresponding to an arbitrary point P (Xp) (Xp, fp (Xp), gp (Xp)) on the top surface geodesic curve on the paper surface Lp (
  • the angle ⁇ ( ⁇ ) and the length 1 ( ⁇ ⁇ ) of the ruled-line projection are known because they can be calculated.
  • the length L t (x p ) and angle) 3 (x p ) on the development paper are unknown. Therefore, if the length L t (x p ) and the angle iS (x p ) on the developed paper surface can be obtained, the paper surface can be estimated, that is, the unknown function g p (x p ) indicating the height of the geodesic curve and And gq (X p ).
  • the angle 0, the length l (x p ) of the ruled line projection, and the width h of the parallel geodesic curve and the angle / 3 (x p ) are related by the following relationship due to the inclination of the ruled line. Holds.
  • the paper surface may be estimated from the projection set of the geodesic line and the weaving line by an iterative method using the sum of deviations from the identity of the length and angle of the geodesic line on the paper surface as an energy function. Good.
  • a paper surface is a straight line on a curved surface that passes through any point on the surface.
  • existing virtual parallel lines that can be extracted from character strings and conductors on the paper are used.
  • a parallel line on a flat paper surface becomes a parallel geodesic line on a curved surface of the paper.
  • (s) + tx D (s) are points on the top and bottom geodesic lines on the curved surface of the paper, respectively, and s is set so that a straight line passing through these two points becomes the insight line .
  • the surface coordinate system (s, t) represents a weaving line by fixing s, while it represents a parallel geodesic line by fixing t.
  • a projection set of geodesic lines is extracted based on a character string or a line of call extracted from an input image. Specifically, after extracting the character components that form the characters in the input image or the line segments that form the ⁇ -line, by combining the character components or line segments that are close to each other, the projection set of the geodesic line is obtained.
  • the point sequence X u , X 1 , X D to be represented can be extracted respectively.
  • the internal division ratio of the line of sight by the internal geodesic line is constant regardless of S, so the internal ratio of the line of sight lines by the two internal geodesic projections For T ⁇ (s) and T j (s), ((1 / T i (s))-1): ((1 / T j (s))-1) is constant.
  • the search for the projection set of the line of sight lines that is, the search for the correspondence between the points on the top geodesic projection and the points on the bottom geodesic projection, is performed so that the sum of deviations from this condition is minimized. Then, we obtain the parameter overnight expressions X u (s) and X D (s).
  • the distortion correction can be realized by associating the curved surface with the input image.
  • the image distortion correction technology according to the present invention can cope with various types of distortion by estimating the curved surface of the paper using the content of the paper as a clue, and can also display the image on the paper in one page. Even when only a part is visible, distortion correction is possible, which is extremely useful.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Processing (AREA)
  • Editing Of Facsimile Originals (AREA)

Abstract

Selon l'invention, à partir de l'image d'un plan de papier, réalisée au moyen d'un dispositif d'imagerie, on extrait un ensemble de projections de lignes géodésiques, parallèles les unes aux autres sur le plan de papier incurvé, en utilisant le contenu sur le plan de papier comme indice, puis un ensemble de projections de lignes réglées formant une surface réglée correspondant au plan de papier incurvé est extrait à partir de l'ensemble de projections de lignes géodésiques. Ensuite, le plan de papier incurvé est estimé à partir de l'ensemble de projections de lignes géodésiques et de lignes réglées et la distorsion de l'image est corrigée sur la base du plan de papier incurvé. Il est ainsi possible de traiter différentes distorsions et de les corriger même si seulement une partie du plan de papier apparaît sur l'image.
PCT/JP2004/002825 2003-10-24 2004-03-05 Programme, dispositif et procede de correction de distorsion d'image et support d'enregistrement comportant un programme de correction de distorsion d'image WO2005041125A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2005514903A JP4047352B2 (ja) 2003-10-24 2004-03-05 画像歪み補正プログラム，画像歪み補正装置並びに画像歪み補正方法
US11/359,096 US7471848B2 (en) 2003-10-24 2006-02-22 Program for correcting image distortion, apparatus for correcting image distortion, method for correcting image distortion, and recording medium storing program for correcting image distortion

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
PCT/JP2003/013665 WO2005041123A1 (fr) 2003-10-24 2003-10-24 Programme, dispositif et procede de correction de la distorsion des images
JPPCT/JP03/13665 2003-10-24

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US11/359,096 Continuation US7471848B2 (en) 2003-10-24 2006-02-22 Program for correcting image distortion, apparatus for correcting image distortion, method for correcting image distortion, and recording medium storing program for correcting image distortion

Publications (1)

Publication Number Publication Date
WO2005041125A1 true WO2005041125A1 (fr) 2005-05-06

Family

ID=34509578

Family Applications (2)

Application Number Title Priority Date Filing Date
PCT/JP2003/013665 WO2005041123A1 (fr) 2003-10-24 2003-10-24 Programme, dispositif et procede de correction de la distorsion des images
PCT/JP2004/002825 WO2005041125A1 (fr) 2003-10-24 2004-03-05 Programme, dispositif et procede de correction de distorsion d'image et support d'enregistrement comportant un programme de correction de distorsion d'image

Family Applications Before (1)

Application Number Title Priority Date Filing Date
PCT/JP2003/013665 WO2005041123A1 (fr) 2003-10-24 2003-10-24 Programme, dispositif et procede de correction de la distorsion des images

Country Status (4)

Country Link
US (1) US7471848B2 (fr)
JP (1) JP4047352B2 (fr)
CN (1) CN100412903C (fr)
WO (2) WO2005041123A1 (fr)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100363940C (zh) * 2005-12-29 2008-01-23 北大方正集团有限公司 一种文稿图像几何畸变的校正方法
JP2008123445A (ja) * 2006-11-15 2008-05-29 Fujitsu Ltd 線織線射影抽出プログラム、線織線射影抽出装置および線織線射影抽出方法
CN100464346C (zh) * 2006-04-29 2009-02-25 北大方正集团有限公司 一种表格图像几何畸变的数字校正方法
JP2010049677A (ja) * 2008-07-04 2010-03-04 Dassault Systemes 案内曲線で定義される面の設計をなすコンピュータ実行方法
JP2010171976A (ja) * 2009-01-22 2010-08-05 Canon Inc 歪み文書画像を補正する方法及びシステム
JP2011222003A (ja) * 2010-04-02 2011-11-04 Dassault Systemes 平行測地線によってモデリングされるパーツの設計
JP2013123167A (ja) * 2011-12-12 2013-06-20 Fuji Xerox Co Ltd 画像処理装置及びプログラム
JP2014019090A (ja) * 2012-07-20 2014-02-03 Seiko Epson Corp ラベル作成システム、ラベル作成方法、印刷装置およびプログラム
JP2015104127A (ja) * 2013-11-20 2015-06-04 富士通株式会社 文書画像の補正装置、補正方法及びスキャナ
JP2015122614A (ja) * 2013-12-24 2015-07-02 カシオ計算機株式会社 画像補正装置、及び画像補正方法、プログラム
CN105678684A (zh) * 2014-11-18 2016-06-15 中兴通讯股份有限公司 一种截取图像的方法及装置
JP2016177430A (ja) * 2015-03-19 2016-10-06 カシオ計算機株式会社 画像補正装置、及び画像補正方法、プログラム
WO2017057679A1 (fr) * 2015-09-30 2017-04-06 ヤマハ株式会社 Dispositif de correction d'image

Families Citing this family (44)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7593595B2 (en) * 2004-08-26 2009-09-22 Compulink Management Center, Inc. Photographic document imaging system
US7330604B2 (en) * 2006-03-02 2008-02-12 Compulink Management Center, Inc. Model-based dewarping method and apparatus
WO2008137051A1 (fr) * 2007-05-01 2008-11-13 Compulink Management Center, Inc. Procédé et système de segmentation de photo-document
US8244062B2 (en) * 2007-10-22 2012-08-14 Hewlett-Packard Development Company, L.P. Correction of distortion in captured images
US20130085935A1 (en) 2008-01-18 2013-04-04 Mitek Systems Systems and methods for mobile image capture and remittance processing
US9842331B2 (en) 2008-01-18 2017-12-12 Mitek Systems, Inc. Systems and methods for mobile image capture and processing of checks
US9298979B2 (en) 2008-01-18 2016-03-29 Mitek Systems, Inc. Systems and methods for mobile image capture and content processing of driver's licenses
US8983170B2 (en) 2008-01-18 2015-03-17 Mitek Systems, Inc. Systems and methods for developing and verifying image processing standards for mobile deposit
US8582862B2 (en) 2010-05-12 2013-11-12 Mitek Systems Mobile image quality assurance in mobile document image processing applications
US8577118B2 (en) * 2008-01-18 2013-11-05 Mitek Systems Systems for mobile image capture and remittance processing
US10685223B2 (en) 2008-01-18 2020-06-16 Mitek Systems, Inc. Systems and methods for mobile image capture and content processing of driver's licenses
US10102583B2 (en) 2008-01-18 2018-10-16 Mitek Systems, Inc. System and methods for obtaining insurance offers using mobile image capture
US7953268B2 (en) * 2008-01-18 2011-05-31 Mitek Systems, Inc. Methods for mobile image capture and processing of documents
CN102084378B (zh) * 2008-05-06 2014-08-27 计算机连接管理中心公司 基于照相机的文档成像
US8437570B2 (en) * 2008-05-23 2013-05-07 Microsoft Corporation Geodesic image and video processing
CN101847202B (zh) * 2009-03-23 2012-11-28 凯迈(洛阳)电子有限公司 光学指纹采集器图像畸变的校正算法
WO2010125041A1 (fr) * 2009-04-27 2010-11-04 St-Ericsson (France) Sas Procédé géométrique de transformation d'une image bidimensionnelle
US8351654B2 (en) * 2009-04-28 2013-01-08 Microsoft Corporation Image processing using geodesic forests
US8322384B2 (en) * 2010-03-05 2012-12-04 Whirlpool Corporation Select-fill dispensing system
US9208393B2 (en) 2010-05-12 2015-12-08 Mitek Systems, Inc. Mobile image quality assurance in mobile document image processing applications
US10891475B2 (en) 2010-05-12 2021-01-12 Mitek Systems, Inc. Systems and methods for enrollment and identity management using mobile imaging
US20110299775A1 (en) * 2010-06-08 2011-12-08 International Business Machines Corporation Correcting page curl in scanned books
US8995012B2 (en) 2010-11-05 2015-03-31 Rdm Corporation System for mobile image capture and processing of financial documents
US8781173B2 (en) 2012-02-28 2014-07-15 Microsoft Corporation Computing high dynamic range photographs
CN102780904A (zh) * 2012-05-31 2012-11-14 新奥特（北京）视频技术有限公司 一种通过左右眼图像网格化显示来调节3d图像的方法
US10883303B2 (en) 2013-01-07 2021-01-05 WexEnergy LLC Frameless supplemental window for fenestration
US9691163B2 (en) 2013-01-07 2017-06-27 Wexenergy Innovations Llc System and method of measuring distances related to an object utilizing ancillary objects
US9230339B2 (en) 2013-01-07 2016-01-05 Wexenergy Innovations Llc System and method of measuring distances related to an object
US8923650B2 (en) 2013-01-07 2014-12-30 Wexenergy Innovations Llc System and method of measuring distances related to an object
US9845636B2 (en) 2013-01-07 2017-12-19 WexEnergy LLC Frameless supplemental window for fenestration
US10196850B2 (en) 2013-01-07 2019-02-05 WexEnergy LLC Frameless supplemental window for fenestration
US10963535B2 (en) 2013-02-19 2021-03-30 Mitek Systems, Inc. Browser-based mobile image capture
US20140279323A1 (en) 2013-03-15 2014-09-18 Mitek Systems, Inc. Systems and methods for capturing critical fields from a mobile image of a credit card bill
US9095423B2 (en) * 2013-03-15 2015-08-04 OrCam Technologies, Ltd. Apparatus and method for providing failed-attempt feedback using a camera on glasses
KR102082301B1 (ko) * 2013-09-30 2020-02-27 삼성전자주식회사 카메라로 촬영한 문서 영상을 스캔 문서 영상으로 변환하기 위한 방법, 장치 및 컴퓨터 판독 가능한 기록 매체
JP6194781B2 (ja) * 2013-12-11 2017-09-13 富士ゼロックス株式会社 画像処理装置及びプログラム
CN103903274B (zh) * 2014-04-22 2016-09-21 四川川大智胜软件股份有限公司 一种小半径大曲率畸变曲面投影校正融合的方法
WO2016024375A1 (fr) * 2014-08-12 2016-02-18 ソニー株式会社 Dispositif de traitement d'image et procédé de traitement d'image
CN108073924B (zh) * 2016-11-17 2021-06-22 富士通株式会社 图像处理方法和装置
IL271006B1 (en) 2017-05-30 2024-05-01 WexEnergy LLC Complementary window without a frame for window design
CN110027342A (zh) * 2017-12-20 2019-07-19 卡西欧计算机株式会社 对纸面进行拍摄而电子化的装置、图像校正方法、翻页装置以及拍摄方法
CN113747130A (zh) * 2020-05-29 2021-12-03 中强光电股份有限公司 产生遮罩的方法及执行此方法的投影装置
US11030488B1 (en) 2020-12-31 2021-06-08 VoyagerX, Inc. Book scanning using machine-trained model
US10991081B1 (en) 2020-12-31 2021-04-27 VoyagerX, Inc. Book scanning using machine-trained model

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0437968A (ja) * 1990-06-01 1992-02-07 Fuji Electric Co Ltd 図書の文字読取方法
JPH05303634A (ja) * 1992-04-28 1993-11-16 Olympus Optical Co Ltd 画像取り込み装置
JPH0795387A (ja) * 1993-06-23 1995-04-07 Ricoh Co Ltd 歪修正装置及び歪修正方法
JPH1091783A (ja) * 1996-09-11 1998-04-10 Ricoh Co Ltd 画像位置合わせ方法、ファクス文字認識装置及びコンピュータ記憶媒体
JPH10173905A (ja) * 1996-12-11 1998-06-26 Minolta Co Ltd 画像読取り装置
JP2002334327A (ja) * 2001-02-23 2002-11-22 Hewlett Packard Co <Hp> ドキュメントのキャプチャに関する改善
JP2003069807A (ja) * 2001-08-27 2003-03-07 Ricoh Co Ltd 画像歪み補正装置、画像読取装置、画像形成装置及びプログラム

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05303635A (ja) 1992-04-28 1993-11-16 Matsushita Electric Ind Co Ltd 画像合成装置
US6018593A (en) 1996-09-11 2000-01-25 Ricoh Company, Ltd. Method and system for correcting image position based upon predetermined pattern portions
US6970592B2 (en) * 2000-09-04 2005-11-29 Fujitsu Limited Apparatus and method for correcting distortion of input image
US6873732B2 (en) * 2001-07-09 2005-03-29 Xerox Corporation Method and apparatus for resolving perspective distortion in a document image and for calculating line sums in images
US7430065B2 (en) * 2001-08-27 2008-09-30 Ricoh Company, Ltd Method and system for correcting distortions in image data scanned from bound originals

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0437968A (ja) * 1990-06-01 1992-02-07 Fuji Electric Co Ltd 図書の文字読取方法
JPH05303634A (ja) * 1992-04-28 1993-11-16 Olympus Optical Co Ltd 画像取り込み装置
JPH0795387A (ja) * 1993-06-23 1995-04-07 Ricoh Co Ltd 歪修正装置及び歪修正方法
JPH1091783A (ja) * 1996-09-11 1998-04-10 Ricoh Co Ltd 画像位置合わせ方法、ファクス文字認識装置及びコンピュータ記憶媒体
JPH10173905A (ja) * 1996-12-11 1998-06-26 Minolta Co Ltd 画像読取り装置
JP2002334327A (ja) * 2001-02-23 2002-11-22 Hewlett Packard Co <Hp> ドキュメントのキャプチャに関する改善
JP2003069807A (ja) * 2001-08-27 2003-03-07 Ricoh Co Ltd 画像歪み補正装置、画像読取装置、画像形成装置及びプログラム

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100363940C (zh) * 2005-12-29 2008-01-23 北大方正集团有限公司 一种文稿图像几何畸变的校正方法
CN100464346C (zh) * 2006-04-29 2009-02-25 北大方正集团有限公司 一种表格图像几何畸变的数字校正方法
JP2008123445A (ja) * 2006-11-15 2008-05-29 Fujitsu Ltd 線織線射影抽出プログラム、線織線射影抽出装置および線織線射影抽出方法
JP2010049677A (ja) * 2008-07-04 2010-03-04 Dassault Systemes 案内曲線で定義される面の設計をなすコンピュータ実行方法
JP2010171976A (ja) * 2009-01-22 2010-08-05 Canon Inc 歪み文書画像を補正する方法及びシステム
KR101741402B1 (ko) 2010-04-02 2017-05-30 다솔 시스템므 평행 지오데식 곡선들에 의해 모델링되는 부품의 설계
JP2011222003A (ja) * 2010-04-02 2011-11-04 Dassault Systemes 平行測地線によってモデリングされるパーツの設計
JP2013123167A (ja) * 2011-12-12 2013-06-20 Fuji Xerox Co Ltd 画像処理装置及びプログラム
JP2014019090A (ja) * 2012-07-20 2014-02-03 Seiko Epson Corp ラベル作成システム、ラベル作成方法、印刷装置およびプログラム
JP2015104127A (ja) * 2013-11-20 2015-06-04 富士通株式会社 文書画像の補正装置、補正方法及びスキャナ
US9589333B2 (en) 2013-12-24 2017-03-07 Casio Computer Co., Ltd. Image correction apparatus for correcting distortion of an image
JP2015122614A (ja) * 2013-12-24 2015-07-02 カシオ計算機株式会社 画像補正装置、及び画像補正方法、プログラム
CN105678684A (zh) * 2014-11-18 2016-06-15 中兴通讯股份有限公司 一种截取图像的方法及装置
JP2018504662A (ja) * 2014-11-18 2018-02-15 ゼットティーイー コーポレイション 画像キャプチャ方法、装置及び記憶媒体
US10419742B2 (en) 2014-11-18 2019-09-17 Xi'an Zhongxing New Software Co. Ltd. Method and device for capturing image and storage medium
CN105678684B (zh) * 2014-11-18 2020-11-03 中兴通讯股份有限公司 一种截取图像的方法及装置
JP2016177430A (ja) * 2015-03-19 2016-10-06 カシオ計算機株式会社 画像補正装置、及び画像補正方法、プログラム
WO2017057679A1 (fr) * 2015-09-30 2017-04-06 ヤマハ株式会社 Dispositif de correction d'image
US10600161B2 (en) 2015-09-30 2020-03-24 Yamaha Corporation Image correction device

Also Published As

Publication number Publication date
WO2005041123A1 (fr) 2005-05-06
CN1853195A (zh) 2006-10-25
CN100412903C (zh) 2008-08-20
JP4047352B2 (ja) 2008-02-13
US7471848B2 (en) 2008-12-30
US20060140504A1 (en) 2006-06-29
JPWO2005041125A1 (ja) 2007-03-29

Similar Documents

Publication Publication Date Title
WO2005041125A1 (fr) Programme, dispositif et procede de correction de distorsion d&#39;image et support d&#39;enregistrement comportant un programme de correction de distorsion d&#39;image
Yamashita et al. Shape reconstruction and image restoration for non-flat surfaces of documents with a stereo vision system
US10289924B2 (en) System and method for scanned document correction
Liang et al. Geometric rectification of camera-captured document images
US9305211B2 (en) Method, apparatus, and computer-readable recording medium for converting document image captured by using camera to dewarped document image
US8587818B2 (en) Captured image processing system and recording medium
CN104735293B (zh) 图像修正装置图像修正方法以及记录介质
US8554012B2 (en) Image processing apparatus and image processing method for correcting distortion in photographed image
CN102194212B (zh) 图像处理方法、装置及系统
CN106331527A (zh) 一种图像拼接方法及装置
JP4877392B2 (ja) 特徴属性計算装置、特徴量抽出装置とパターン照合装置と方法及びプログラム
US20060061777A1 (en) Modifying digital documents
WO2012029658A1 (fr) Dispositif d&#39;imagerie, dispositif de traitement d&#39;image, procédé de traitement d&#39;image et programme de traitement d&#39;image
JP2013128229A (ja) 画像印刷装置、方法、プログラム、画像処理装置、方法及びプログラム
JP7033439B2 (ja) 石垣管理システム、石垣管理方法及びコンピュータプログラム
Dinesh et al. Adaptive nonrigid inpainting of three-dimensional point cloud geometry
TW522715B (en) Image processing method and contactless image input apparatus utilizing the method
JPH0935062A (ja) 画像処理方法
JP4946376B2 (ja) 線織線射影抽出プログラム、線織線射影抽出装置および線織線射影抽出方法
US20210390328A1 (en) Optical character recognition of documents having non-coplanar regions
JP2006113832A (ja) ステレオ画像処理装置およびプログラム
KR101028171B1 (ko) 3차원 원근투영법에 기초하여 카메라에 투영된 사각형 문서에 대한 가로대 세로 비를 결정하는 방법
JPWO2004077356A1 (ja) 画像結合装置、画像結合方法
JP2009025992A (ja) ２次元コード
RU2820743C1 (ru) Способ получения ректифицированных изображений документов, сложенных пополам

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 200480026638.7

Country of ref document: CN

AK Designated states

Kind code of ref document: A1

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): BW GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
WWE Wipo information: entry into national phase

Ref document number: 2005514903

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 11359096

Country of ref document: US

WWP Wipo information: published in national office

Ref document number: 11359096

Country of ref document: US

122 Ep: pct application non-entry in european phase